unbuilt.app: Skill for Claude Code

.agents/skills/unbuilt/SKILL.md

unbuilt is a skill for Claude Code, Codex from yavorsky/unbuilt.app. It costs 73 tokens per session (500 once invoked), scanned A, original, MIT.

A command-line tool that examines a live website and identifies the technologies behind it, such as its framework, interface library, bundler, styling system, and analytics.

In plain words
What is it for?
Use it to analyze a website URL, inspect a competitor’s technology choices, or gather implementation details before building something similar.
Why use it?
It reduces the guesswork involved in understanding how an existing website was built. That information helps when comparing technical choices or planning a similar application.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is yavorsky/unbuilt.app's own configuration. It tells Claude Code and Codex how to work on unbuilt.app itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything unbuilt.app configures →

Reuse

Borrowing it

Nothing to install: this file belongs to yavorsky/unbuilt.app. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/yavorsky/unbuilt.app/main/.agents/skills/unbuilt/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/yavorsky/unbuilt.app

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for unbuilt

README.md
[![agentmods](https://agentmods.dev/badge/skills/yavorsky/unbuilt.app/unbuilt/github.svg)](https://agentmods.dev/skills/yavorsky/unbuilt.app/unbuilt)
Your own site
<a href="https://agentmods.dev/skills/yavorsky/unbuilt.app/unbuilt"><img src="https://agentmods.dev/badge/skills/yavorsky/unbuilt.app/unbuilt/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for unbuilt

Your own site · 80×15
<a href="https://agentmods.dev/skills/yavorsky/unbuilt.app/unbuilt"><img src="https://agentmods.dev/badge/skills/yavorsky/unbuilt.app/unbuilt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.00500
Opus 5 $0.00036 $0.00250
Sonnet 5 $0.00015 $0.00100
Haiku 4.5 $0.00007 $0.00050

Measured 9d ago against content hash 887ffe29e4dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

unbuilt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.agents/skills/unbuilt/SKILL.md · 71 lines

What it actually says

unbuilt

Detect the complete technology stack of any website using live code analysis.

When to use

  • User asks "what tech stack does [website] use?"
  • User says "build me something like [website]" — analyze it first
  • User wants to compare tech stacks of different sites
  • User needs to understand a competitor's technical choices

Prerequisites

Requires Node.js >= 20. Install if not present:

npm install -g @unbuilt/cli

Analyze a website

unbuilt <url> --format agent

Always use --format agent — it returns compact one-line-per-category output optimized for your context window.

Example output:

Framework: Next.js
UI: React
Bundler: Webpack
Styling: Tailwind CSS + PostCSS
State: Zustand
Tables: TanStack Table + TanStack Virtual
Components: Radix UI
Animation: Framer Motion
Router: Next.js Router
Monitoring: Sentry

Alternative output formats

Only use these if the user explicitly asks for more detail:

  • --json — full structured JSON with confidence scores and matched patterns
  • No flag — default table output with all categories

Remote analysis

If Playwright fails or takes too long:

unbuilt <url> --remote --format agent

Uses unbuilt.app servers with cached results.

Detection categories

Framework, UI Library, Bundler, Styling, Component Library (Radix, Headless UI, Ant Design), State Management, Tables/Virtualization (TanStack Table, AG Grid, Virtuoso), Forms (React Hook Form, Formik, Zod), Animation (Framer Motion, GSAP, Lottie), API Patterns (GraphQL, tRPC, WebSocket, SSE), HTTP Client, Router, Translations, Dates, Transpiler, Monitoring, Analytics, Platform.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 71 lines · 73 tokens per session scan A 887ffe29e4dd

Subscribe to this mod's changes

unbuilt is a skill published in the GitHub repository yavorsky/unbuilt.app (92 stars, last pushed 19d ago), licensed MIT. It adds 73 tokens to every session and 500 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.